One of Pecan’s customers is a large, multinational CPG company. The company sources ingredients from suppliers all over the globe. The company also supplies products and services to thousands of buyers who distribute them to restaurants, pubs, shops, supermarkets, vending machines, etc.
The company's customers (the buyers) are one of its biggest assets, the engine of the business, and are responsible for its future growth. Yet, the company is losing customers for unknown reasons, inflicting damages on sales operations, cash flow and revenues.
The CPG company was seeking a solution that will identify early warnings of churn per individual buyer while understanding the factors behind each churn in order to enact preventive measures to mitigate it. Furthermore, the company needed a macro outlook to identify the most common factors of churn among all of its customers, providing insights to transform sales, marketing, and channels’ strategies in order to decrease overall churn.
Before turning to Pecan, the customer used other statistical and manual methods to predict the number of customers that are at high risk for churn.
The company used Pecan to build 2 deep learning-based predictive analytics models:
The customer used the Pecan platform to build the 2 models within 10 days, compared with 4-6 months required by alternative solutions, which also consume huge and expensive resources of data scientists.
Using Pecan instead of traditional methods meant that the cost of the project is estimated at $30,000 - $50,000, compared with a rough estimate of $150,000-$500,000 in alternative solutions.
Furthermore, the AI models were built by one of the customer’s BI managers using the Pecan platform, avoiding the need for a trained and expensive data scientists.
“We developed predictive processes at a fraction of the standard time. Coupled with Pecan’s performance and security, the ROI was instant”
CIO of the multinational CPG company
Using the first model built using Pecan, the customer was able to identify 270% more customers at risk of churn than with other solutions. Using the second AI model built using Pecan, the customer was able to predict 280% more customers at risk of churn - as well as the specific factors driving churn for each customer.
In addition, Pecan listed 5 specific factors that contributed most to each customer’s tendency to churn. Some of the most common contributing factors were:
The customer used this information to empower their retention team in identifying incentives that will prevent specific customers to churn, therefore increasing revenues.
Before using Pecan’s predictive analytics platform, the company’s retention team was able to prevent churn, calculated at $100,000 in revenue. Using Pecan, they were able to generate around $370,000, an additional $270,000 additional revenue.
Using Pecan, the customer discovered the 5 most impactful factors behind churn among all customers. This critical information was used to adjust sales, marketing and channel plan to holistically address the churn challenge, therefore increasing customer loyalty and revenues, as well as drive growth.
Most critically the customer empowered its BI team with the capability of building state of the art AI predictive analytics models, without the need to hire data scientists for the job.